Studiu Covid SUUB

Report

1 Define functions

## Define function that recodes to numeric, but watches out to coercion to not introduce NAs
colstonumeric <- function(df){
  tryCatch({
    df_num <- as.data.frame(
      lapply(df,
             function(x) { as.numeric(as.character(x))})) 
  },warning = function(stop_on_warning) {
    message("Stoped the execution of numeric conversion: ", conditionMessage(stop_on_warning))
  }) 
}
##
## Define function that reverse codes items
ReverseCode <- function(df, tonumeric = FALSE, min = NULL, max = NULL) {
  if(tonumeric) df <- colstonumeric(df)
  df <- (max + min) - df
}
##


# Scores
## Define function that scores only rows with less than 10% NAs (returns NA if all or above threshold percentage of rows are NA); can reverse code if vector of column indexes and min, max are provided.
ScoreLikert <- function(df, stat = c("sum", "mean"), imputena = c(FALSE, "zero", "mean", "median"), 
                        napercent = .1, tonumeric = FALSE, reversecols = NULL, min = NULL, max = NULL) {
  stat <- match.arg(stat)
  imputena <- match.arg(imputena)
  reverse_list <- list(reversecols = reversecols, min = min, max = max)
  reverse_check <- !sapply(reverse_list, is.null)
  
  # Recode to numeric, but watch out to coercion to not introduce NAs
  colstonumeric <- function(df){
    tryCatch({
      df_num <- as.data.frame(
        lapply(df,
               function(x) { as.numeric(as.character(x))})) 
    },warning = function(stop_on_warning) {
      message("Stoped the execution of numeric conversion: ", conditionMessage(stop_on_warning))
    }) 
  }
  
  if(tonumeric) df <- colstonumeric(df)
  
  if(all(reverse_check)){
    df[ ,reversecols] <- (max + min) - df[ ,reversecols]
  }else if(any(reverse_check)){
    stop("Insuficient info for reversing. Please provide: ", paste(names(reverse_list)[!reverse_check], collapse = ", "))
  }
  
  if(tonumeric) df <- colstonumeric(df)                           
  
  if(imputena == "zero") df[is.na(df)] <- 0                            # NAs to 0 can help when stat = "mean" with na.rm = T because it keeps denominator constant
  if(imputena == "mean") {                                             # replace NA with row means, the denominator of this mean is the number of completed items
    # index_na <- which(is.na(df), arr.ind = TRUE)                    # for some reason doesnt work on tibbles
    # df[index_na] <- rowMeans(df, na.rm=TRUE)[index_na[, 1]]
    df <- t(apply(df, 1, function(x) replace(x, is.na(x), mean(x, na.rm = TRUE))))
  }
  if(imputena == "median") {                                             # replace NA with row medians
    df <- t(apply(df, 1, function(x) replace(x, is.na(x), median(x, na.rm = TRUE))))
} 
  
  if(stat == "sum"){
    df_res <- ifelse(rowSums(is.na(df)) > ncol(df) * napercent,
                     NA,
                     rowSums(df, na.rm = TRUE) * NA ^ (rowSums(!is.na(df)) == 0))
  }
  if(stat == "mean"){
    df_res <- ifelse(rowSums(is.na(df)) > ncol(df) * napercent,
                     NA,
                     rowMeans(df, na.rm = TRUE) * NA ^ (rowSums(!is.na(df)) == 0))
  }
  return(df_res)
}
##


# Tests --- Don't Run
# bla <- mtcars[, 8:11]
# 
# bla[1, 4] <- NA
# bla[2, 3] <- NA; bla[2, 4] <- NA 
# bla[3, 2] <- NA; bla[3, 3] <- NA; bla[3, 4] <- NA 
# 
# bla$Tot <- ScoreLikert(bla[, 1:4]) 
# bla$Tot2 <- ScoreLikert(bla[, 1:4], napercent = .9) 
# bla$Tot3 <- ScoreLikert(bla[, 1:4], imputena = "zero", napercent = .1)
# bla$Tot4 <- ScoreLikert(bla[, 1:4], stat = "mean", imputena = "zero", napercent = .1)
# bla$Tot5 <- ScoreLikert(bla[, 1:4], stat = "sum", imputena = "zero", napercent = .1)
# bla$Tot6 <- ScoreLikert(bla[, 1:4], stat = "sum", imputena = "mean", napercent = .9)

2 Read data

#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
# Read, Clean, Recode, Unite
#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

## Read files
folder <- "C:/Users/Mihai/Desktop/R Notebooks/notebooks/municipal-covid"
file <- "Cercetare SUUB - Covid 2020.xlsx"

setwd(folder)

# Read data
Data <- rio::import(file.path(folder, file),
                    skip = 0, which = "Sheet2")  

# Exclude last 3 rows: empty and other info
Data <- Data[-c(133:135),]

3 Clean, Transform, Score scales

## Cutoffs
cutoffPCL <- 32   # literature: 31-33 or 38 
algPCL <- data.frame(B = 1, C = 1, D = 2, E = 2)

cutoffMBI_Ex <- 2.20  
cutoffMBI_Cy <- 2
##


# Define column index:  index = col index; itemindex = index of item in questionnaire
indexDASS <- 22:42
indexMBI <- 43:58
indexCERQ <- 59:94
indexPCL <- 95:114

itemindexMBI_Ex <- c(1, 3, 5, 11, 14)      # Emotional Exhaustion
itemindexMBI_Cy <- c(2, 7, 8, 13, 15)      # Cynicism
itemindexMBI_Pe <- c(4, 6, 9, 10, 12, 16)  # Professional Efficacy

itemindexDASS_S <- c(1, 6, 8, 11, 12, 14, 18)
itemindexDASS_D <- c(3, 5, 10, 13, 16, 17, 21)
itemindexDASS_A <- c(2, 4, 7, 9, 15, 19, 20)

itemindexCERQ_Sbl <- c(1, 10, 19, 28)  # Self-blame
itemindexCERQ_Acc <- c(2, 11, 20, 29)  # Acceptance
itemindexCERQ_Rum <- c(3, 12, 21, 30)  # Rumination
itemindexCERQ_PRf <- c(4, 13, 22, 31)  # Positive Refocusing
itemindexCERQ_RPl <- c(5, 14, 23, 32)  # Refocus on Planning
itemindexCERQ_PRa <- c(6, 15, 24, 33)  # Positive Reappraisal
itemindexCERQ_PPe <- c(7, 16, 25, 34)  # Putting into Perspective
itemindexCERQ_Cat <- c(8, 17, 26, 35)  # Catastrophizing
itemindexCERQ_Obl <- c(9, 18, 27, 36)  # Other-blame

# Rename columns
# names(Data)[1:12] <- stringr::str_replace_all(names(Data)[1:12], "[[:blank:]]", "_")
Data <- janitor::clean_names(Data)
names(Data)[1] <- "ID"
names(Data)[names(Data) %in% names(Data[, indexDASS])]  <- c(sprintf("DASS_%01d", seq(1, 21)))
names(Data)[names(Data) %in% names(Data[, indexMBI])]  <- c(sprintf("MBI_%01d", seq(1, 16)))
names(Data)[names(Data) %in% names(Data[, indexCERQ])]  <- c(sprintf("CERQ_%01d", seq(1, 36)))
names(Data)[names(Data) %in% names(Data[, indexPCL])]  <- c(sprintf("PCL_%01d", seq(1, 20)))

# Transform general info
to_num_cols <- c(2, 5, 6)  # "varsta", "copii", "nepoti"
to_fac_cols <- c(3, 4, 7:21)

Data <-
  Data %>%
  dplyr::mutate_at(vars(to_num_cols), as.numeric) %>%
  dplyr::mutate_at(vars(to_fac_cols), as.factor)

# Transfomr item scores to numeric
Data[, indexDASS] <- colstonumeric(Data[, indexDASS])
Data[, indexMBI] <- colstonumeric(Data[, indexMBI])
Data[, indexCERQ] <- colstonumeric(Data[, indexCERQ])
Data[, indexPCL] <- colstonumeric(Data[, indexPCL])


# Score CERQ
Data$CERQ_Sbl  <- ScoreLikert(Data[, c(sprintf("CERQ_%01d", itemindexCERQ_Sbl))], stat = "sum", imputena = "mean", napercent = 1)
Data$CERQ_Acc  <- ScoreLikert(Data[, c(sprintf("CERQ_%01d", itemindexCERQ_Acc))], stat = "sum", imputena = "mean", napercent = 1)
Data$CERQ_Rum  <- ScoreLikert(Data[, c(sprintf("CERQ_%01d", itemindexCERQ_Rum))], stat = "sum", imputena = "mean", napercent = 1)
Data$CERQ_PRf  <- ScoreLikert(Data[, c(sprintf("CERQ_%01d", itemindexCERQ_PRf))], stat = "sum", imputena = "mean", napercent = 1)
Data$CERQ_RPl  <- ScoreLikert(Data[, c(sprintf("CERQ_%01d", itemindexCERQ_RPl))], stat = "sum", imputena = "mean", napercent = 1)
Data$CERQ_PRa  <- ScoreLikert(Data[, c(sprintf("CERQ_%01d", itemindexCERQ_PRa))], stat = "sum", imputena = "mean", napercent = 1)
Data$CERQ_PPe  <- ScoreLikert(Data[, c(sprintf("CERQ_%01d", itemindexCERQ_PPe))], stat = "sum", imputena = "mean", napercent = 1)
Data$CERQ_Cat  <- ScoreLikert(Data[, c(sprintf("CERQ_%01d", itemindexCERQ_PPe))], stat = "sum", imputena = "mean", napercent = 1)


# Score DASS
Data$DASS_S  <- ScoreLikert(Data[, c(sprintf("DASS_%01d", itemindexDASS_S))], napercent = 1)
Data$DASS_D  <- ScoreLikert(Data[, c(sprintf("DASS_%01d", itemindexDASS_D))], napercent = 1)
Data$DASS_A  <- ScoreLikert(Data[, c(sprintf("DASS_%01d", itemindexDASS_A))], napercent = 1)

# Correct MBI error (MBI items scores are 0-6, while in data item scores range 0-7)
Data[, indexMBI] <-
  Data[, indexMBI] %>%
  dplyr::mutate_all(~ifelse(. == 7, 6, .))

# Score MBI
Data$MBI_Total <- ScoreLikert(Data[, indexMBI], napercent = .3, stat = "mean", imputena = "zero")
Data$MBI_Ex <- ScoreLikert(Data[, c(sprintf("MBI_%01d", itemindexMBI_Ex))], napercent = 1, stat = "mean", imputena = "zero")
Data$MBI_Cy <- ScoreLikert(Data[, c(sprintf("MBI_%01d", itemindexMBI_Cy))], napercent = 1, stat = "mean", imputena = "zero")
Data$MBI_Pe <- ScoreLikert(Data[, c(sprintf("MBI_%01d", itemindexMBI_Pe))], napercent = 1, stat = "mean", imputena = "zero")

# Score PCL
Data$PCL_Total <- ScoreLikert(Data[, indexPCL], napercent = .3)               # NA if NA threshold is exceeded 
Data$PCL_B <- ScoreLikert(Data[, c(sprintf("PCL_%01d", 1:5))], napercent = 1)    # do nothing if NA threshold is exceeded
Data$PCL_C <- ScoreLikert(Data[, c(sprintf("PCL_%01d", 6:7))], napercent = 1) 
Data$PCL_D <- ScoreLikert(Data[, c(sprintf("PCL_%01d", 8:14))], napercent = 1)  
Data$PCL_E <- ScoreLikert(Data[, c(sprintf("PCL_%01d", 15:20))], napercent = 1)



# ---
# PCL Diagnostic Algorithm
itemsPCL_B <- c(sprintf("PCL_%01d", 1:5))
itemsPCL_C <- c(sprintf("PCL_%01d", 6:7))
itemsPCL_D <- c(sprintf("PCL_%01d", 8:14))
itemsPCL_E <- c(sprintf("PCL_%01d", 15:20))

DataPCLAlg <-  
  Data %>% 
  dplyr::select(tidyselect::all_of(indexPCL)) %>% 
  dplyr::mutate_all(
    funs(case_when(
      . >=2 ~ 1,
      # . <2 ~ 0,
      is.na(.) ~ 0,
      TRUE  ~  0))) %>% 
  
  mutate(PCL_CritB = case_when(rowSums(.[,itemsPCL_B], na.rm = TRUE) >= algPCL$B ~ 1,      # algPCL <- data.frame(B = 1, C = 1, D = 2, E = 2)
                               # rowSums(.[,itemsPCL_B], na.rm = TRUE) <1 ~ 0,
                               TRUE  ~  0)) %>% 
  mutate(PCL_CritC = case_when(rowSums(.[,itemsPCL_C], na.rm = TRUE) >= algPCL$C ~ 1,    
                               # rowSums(.[,itemsPCL_C], na.rm = TRUE) <1 ~ 0,
                               TRUE  ~  0)) %>% 
  mutate(PCL_CritD = case_when(rowSums(.[,itemsPCL_D], na.rm = TRUE) >= algPCL$D ~ 1,   
                               # rowSums(.[,itemsPCL_D], na.rm = TRUE) <1 ~ 0,
                               TRUE  ~  0)) %>% 
  mutate(PCL_CritE = case_when(rowSums(.[,itemsPCL_E], na.rm = TRUE) >= algPCL$E ~ 1,    
                               # rowSums(.[,itemsPCL_E], na.rm = TRUE) <1 ~ 0,
                               TRUE  ~  0)) %>% 
  mutate(PCL_Alg = case_when(PCL_CritB == 1 & PCL_CritC == 1 & PCL_CritD == 1 & PCL_CritE == 1 ~ 1,
                             TRUE  ~  0)) 

# Cutoffs
Data$PCL_cut <- ifelse(Data$PCL_Total >= cutoffPCL, 1, 0)
Data$PCLAlg <- DataPCLAlg$PCL_Alg

Data$MBI_Ex_cut <- ifelse(Data$MBI_Ex >= cutoffMBI_Ex, 1, 0)
Data$MBI_Cy_cut <- ifelse(Data$MBI_Cy >= cutoffMBI_Cy, 1, 0)
Data$MBI_cut <- ifelse(Data$MBI_Ex_cut | Data$MBI_Cy_cut, 1, 0)
# ---

4 Descriptives

knitr::asis_output("## Basic description for dataframe")

Basic description for dataframe

introduce(Data)

# knitr::asis_output("## Basic description for dataframe")
Data[, -indexAllItems] %>%
  dplyr::rename_all(~stringr::str_replace_all( ., "_", " " ))  %>% 
  dplyr::rename_all(~stringr::str_wrap(., 20)) %>%
  summarytools::dfSummary(plain.ascii = FALSE, style = "grid", 
                        graph.magnif = 0.75, valid.col = FALSE) %>%
  print(method = 'render')

Data Frame Summary

N: 132

No	Variable	Stats / Values	Freqs (% of Valid)	Graph	Missing
1	ID [numeric]	mean (sd) : 66.5 (38.25) min < med < max : 1 < 66.5 < 132 IQR (CV) : 65.5 (0.58)	132 distinct values		0 (0%)
2	varsta [numeric]	mean (sd) : 2.83 (1.05) min < med < max : 1 < 3 < 5 IQR (CV) : 1.5 (0.37)	1 : 18 (13.7%) 2 : 25 (19.1%) 3 : 55 (42.0%) 4 : 27 (20.6%) 5 : 6 (4.6%)		1 (0.76%)
3	gen [factor]	1. 1 2. 2	16 (12.1%) 116 (87.9%)		0 (0%)
4	status marital [factor]	1. 0 2. 1 3. 2 4. 3 5. 4	1 (0.8%) 39 (29.5%) 74 (56.1%) 16 (12.1%) 2 (1.5%)		0 (0%)
5	copii [numeric]	mean (sd) : 0.88 (0.86) min < med < max : 0 < 1 < 4 IQR (CV) : 1 (0.98)	0 : 49 (37.4%) 1 : 55 (42.0%) 2 : 23 (17.6%) 3 : 2 (1.5%) 4 : 2 (1.5%)		1 (0.76%)
6	nepoti [numeric]	mean (sd) : 0.41 (1.02) min < med < max : 0 < 0 < 6 IQR (CV) : 0 (2.48)	0 : 104 (79.4%) 1 : 14 (10.7%) 2 : 7 (5.3%) 4 : 5 (3.8%) 6 : 1 (0.8%)		1 (0.76%)
7	domiciliu [factor]	1. 0 2. 1 3. 2 4. 3	1 (0.8%) 109 (82.6%) 5 (3.8%) 17 (12.9%)		0 (0%)
8	scoala absolvita [factor]	1. 1 2. 2 3. 3	1 (0.8%) 63 (47.7%) 68 (51.5%)		0 (0%)
9	ani de lucru in domeniu [factor]	1. 1 2. 2 3. 3 4. 4 5. 5	25 (19.1%) 24 (18.3%) 13 (9.9%) 22 (16.8%) 47 (35.9%)		1 (0.76%)
10	profesie ocupatie [factor]	1. 1 2. 2 3. 3 4. 4 5. 5	22 (16.8%) 92 (70.2%) 11 (8.4%) 2 (1.5%) 4 (3.0%)		1 (0.76%)
11	sectia pe care desfasurati activitatea [factor]	1. 1 2. 12 3. 14 4. 16 5. 18 6. 2 7. 20 8. 21 9. 3 10. 4 [ 4 others ]	32 (24.2%) 5 (3.8%) 1 (0.8%) 9 (6.8%) 8 (6.1%) 13 (9.8%) 3 (2.3%) 23 (17.4%) 4 (3.0%) 3 (2.3%) 31 (23.5%)		0 (0%)
12	pe sectia pe care lucrati au fost de la inceputul pandemiei cu covid 19 depistate cazuri pozitive [factor]	1. 1 2. 2	117 (89.3%) 14 (10.7%)		1 (0.76%)
13	care a fost programul de lucru in timpul starii de urgenta [factor]	1. 1 2. 2 3. 7	16 (12.2%) 114 (87.0%) 1 (0.8%)		1 (0.76%)
14	care a fost numarul de garzi in timpul starii de urgenta [factor]	1. 1 2. 2 3. 3 4. 4 5. 5 6. 6	2 (1.5%) 1 (0.8%) 5 (3.8%) 9 (6.9%) 57 (43.5%) 57 (43.5%)		1 (0.76%)
15	ati fost testat a pentru sars cov 2 in aceasta perioada de la inceputul pamdemiei [factor]	1. 1 2. 2	123 (93.9%) 8 (6.1%)		1 (0.76%)
16	daca da de cate ori [factor]	1. 1 2. 2 3. 3 4. 4 5. 5 6. 6	58 (44.3%) 39 (29.8%) 16 (12.2%) 9 (6.9%) 7 (5.3%) 2 (1.5%)		1 (0.76%)
17	in conditiile in care ati fost testat a cate zile ati asteptat rezultatul testului [factor]	1. 1 2. 2 3. 3 4. 4	103 (78.6%) 15 (11.5%) 3 (2.3%) 10 (7.6%)		1 (0.76%)
18	daca da care a fost rezultatul [factor]	1. 1 2. 2 3. 3	24 (18.3%) 99 (75.6%) 8 (6.1%)		1 (0.76%)
19	in urma rezultatului pozitiv al testului ati stat [factor]	1. 2 2. 3 3. 4 4. 5	2 (1.5%) 16 (12.2%) 112 (85.5%) 1 (0.8%)		1 (0.76%)
20	desi nu ati fost depistat pozitiv dar ati avut contact cu colegi pacienti care au fost depistati pozitiv cu sars cov 2 unde ati stat in izolare [factor]	1. 1 2. 2 3. 3 4. 4 5. 5	19 (14.5%) 27 (20.6%) 3 (2.3%) 1 (0.8%) 81 (61.8%)		1 (0.76%)
21	pe o scala de la 1 la 10 dati o nota pentru cat de daunator sanatatii dvs considerati ca ar putea fi virusul sars cov 2 [factor]	1. 1 2. 10 3. 11 4. 2 5. 3 6. 4 7. 5 8. 6 9. 7 10. 8 [ 1 others ]	10 (7.6%) 44 (33.6%) 2 (1.5%) 2 (1.5%) 3 (2.3%) 4 (3.1%) 12 (9.2%) 8 (6.1%) 14 (10.7%) 18 (13.7%) 14 (10.7%)		1 (0.76%)
22	CERQ Sbl [numeric]	mean (sd) : 8.27 (3.44) min < med < max : 3 < 8 < 20 IQR (CV) : 5 (0.42)	17 distinct values		0 (0%)
23	CERQ Acc [numeric]	mean (sd) : 11.16 (4.04) min < med < max : 4 < 10 < 20 IQR (CV) : 6 (0.36)	16 distinct values		0 (0%)
24	CERQ Rum [numeric]	mean (sd) : 11.48 (4.09) min < med < max : 4 < 11 < 20 IQR (CV) : 5 (0.36)	17 distinct values		0 (0%)
25	CERQ PRf [numeric]	mean (sd) : 12.78 (4.59) min < med < max : 4 < 12 < 20 IQR (CV) : 8 (0.36)	17 distinct values		0 (0%)
26	CERQ RPl [numeric]	mean (sd) : 15.1 (4.03) min < med < max : 4 < 16 < 20 IQR (CV) : 6.25 (0.27)	17 distinct values		0 (0%)
27	CERQ PRa [numeric]	mean (sd) : 15.46 (3.82) min < med < max : 4 < 16 < 20 IQR (CV) : 4 (0.25)	16 distinct values		0 (0%)
28	CERQ PPe [numeric]	mean (sd) : 13.9 (4) min < med < max : 4 < 14 < 20 IQR (CV) : 6 (0.29)	16 distinct values		0 (0%)
29	CERQ Cat [numeric]	mean (sd) : 13.9 (4) min < med < max : 4 < 14 < 20 IQR (CV) : 6 (0.29)	16 distinct values		0 (0%)
30	DASS S [numeric]	mean (sd) : 4.94 (4.25) min < med < max : 0 < 4 < 17 IQR (CV) : 5 (0.86)	16 distinct values		0 (0%)
31	DASS D [numeric]	mean (sd) : 3.12 (3.64) min < med < max : 0 < 2 < 17 IQR (CV) : 5 (1.17)	14 distinct values		0 (0%)
32	DASS A [numeric]	mean (sd) : 3.05 (3.97) min < med < max : 0 < 1 < 20 IQR (CV) : 5 (1.3)	17 distinct values		0 (0%)
33	MBI Total [numeric]	mean (sd) : 1.36 (1.17) min < med < max : 0 < 0.97 < 4.94 IQR (CV) : 1.58 (0.86)	53 distinct values		0 (0%)
34	MBI Ex [numeric]	mean (sd) : 2.14 (1.6) min < med < max : 0 < 1.8 < 6 IQR (CV) : 2.6 (0.75)	31 distinct values		0 (0%)
35	MBI Cy [numeric]	mean (sd) : 1.27 (1.33) min < med < max : 0 < 1 < 6 IQR (CV) : 1.45 (1.05)	24 distinct values		0 (0%)
36	MBI Pe [numeric]	mean (sd) : 0.8 (1.16) min < med < max : 0 < 0.17 < 5 IQR (CV) : 1 (1.46)	24 distinct values		0 (0%)
37	PCL Total [numeric]	mean (sd) : 15.95 (13.63) min < med < max : 0 < 11.5 < 63 IQR (CV) : 19 (0.85)	41 distinct values		0 (0%)
38	PCL B [numeric]	mean (sd) : 4.38 (4.35) min < med < max : 0 < 3 < 16 IQR (CV) : 5 (0.99)	17 distinct values		0 (0%)
39	PCL C [numeric]	mean (sd) : 1.95 (2.23) min < med < max : 0 < 1 < 8 IQR (CV) : 3 (1.14)	0 : 48 (36.4%) 1 : 25 (18.9%) 2 : 18 (13.6%) 3 : 11 (8.3%) 4 : 11 (8.3%) 5 : 6 (4.5%) 6 : 6 (4.5%) 7 : 2 (1.5%) 8 : 5 (3.8%)		0 (0%)
40	PCL D [numeric]	mean (sd) : 4.33 (5.12) min < med < max : 0 < 2 < 22 IQR (CV) : 7 (1.18)	19 distinct values		0 (0%)
41	PCL E [numeric]	mean (sd) : 5.29 (4.21) min < med < max : 0 < 4 < 17 IQR (CV) : 5.25 (0.8)	18 distinct values		0 (0%)
42	PCL cut [numeric]	mean (sd) : 0.12 (0.33) min < med < max : 0 < 0 < 1 IQR (CV) : 0 (2.7)	0 : 116 (87.9%) 1 : 16 (12.1%)		0 (0%)
43	PCLAlg [numeric]	mean (sd) : 0.14 (0.34) min < med < max : 0 < 0 < 1 IQR (CV) : 0 (2.53)	0 : 114 (86.4%) 1 : 18 (13.6%)		0 (0%)
44	MBI Ex cut [numeric]	mean (sd) : 0.45 (0.5) min < med < max : 0 < 0 < 1 IQR (CV) : 1 (1.1)	0 : 72 (54.5%) 1 : 60 (45.5%)		0 (0%)
45	MBI Cy cut [numeric]	mean (sd) : 0.22 (0.42) min < med < max : 0 < 0 < 1 IQR (CV) : 0 (1.89)	0 : 103 (78.0%) 1 : 29 (22.0%)		0 (0%)
46	MBI cut [numeric]	mean (sd) : 0.48 (0.5) min < med < max : 0 < 0 < 1 IQR (CV) : 1 (1.03)	0 : 68 (51.5%) 1 : 64 (48.5%)		0 (0%)

Generated by summarytools 0.8.8 (R version 3.6.1)
2021-03-19

knitr::asis_output("## Frequency distribution of all discrete variables")

Frequency distribution of all discrete variables

plot_bar(Data)

# knitr::asis_output("## Frequency distribution of all discrete variables by PCL cutoff")
# plot_bar(Data, by = "PCL_cut")
# 
# knitr::asis_output("## Frequency distribution of all discrete variables by PCL diagnostic alg")
# plot_bar(Data, by = "PCLAlg")
# 
# knitr::asis_output("## Frequency distribution of all discrete variables by MBI cutoff")
# plot_bar(Data, by = "MBI_cut")

knitr::asis_output("## View histogram of all continuous variables")

View histogram of all continuous variables

Data %>%
  dplyr::select(-all_of(c(indexDASS, indexMBI, indexCERQ, indexPCL))) %>%       # exclude items
  plot_histogram()

4.1 Rename / compute grouping variables

5 Tests - Item Covid Cases (no. 9 in xlsx, 12 in data)

ggstatsplot::ggbetweenstats(
  data = Data,
  x = cazuri_pe_sectie, y = MBI_Total,
  type = "nonparametric",
  title = "Burnout Total")

ggstatsplot::ggbetweenstats(
  data = Data,
  x = cazuri_pe_sectie, y = PCL_Total,
  type = "nonparametric",
  title = "PTSD Total")

ggstatsplot::ggbetweenstats(
  data = Data,
  x = cazuri_pe_sectie, y = DASS_A,
  type = "nonparametric",
  title = "Anxiety")

ggstatsplot::ggbetweenstats(
  data = Data,
  x = cazuri_pe_sectie, y = DASS_S,
  type = "nonparametric",
  title = "Stress")

ggstatsplot::ggbetweenstats(
  data = Data,
  x = cazuri_pe_sectie, y = DASS_D,
  type = "nonparametric",
  title = "Depression")

6 Tests - Item Expunere (no. 12 in xlsx, 15 in data)

ggstatsplot::ggbetweenstats(
  data = Data,
  x = expunere, y = MBI_Total,
  type = "nonparametric",
  title = "Burnout Total")

ggstatsplot::ggbetweenstats(
  data = Data,
  x = expunere, y = PCL_Total,
  type = "nonparametric",
  title = "PTSD Total")

ggstatsplot::ggbetweenstats(
  data = Data,
  x = expunere, y = DASS_A,
  type = "nonparametric",
  title = "Anxiety")

ggstatsplot::ggbetweenstats(
  data = Data,
  x = expunere, y = DASS_S,
  type = "nonparametric",
  title = "Stress")

ggstatsplot::ggbetweenstats(
  data = Data,
  x = expunere, y = DASS_D,
  type = "nonparametric",
  title = "Depression")

7 Tests - Item Sectii (no. 8 in xlsx, releveled in data)

ggstatsplot::ggbetweenstats(
  data = Data,
  x = sectie_categ, y = MBI_Total,
  type = "nonparametric",
  title = "Burnout Total")

ggstatsplot::ggbetweenstats(
  data = Data,
  x = sectie_categ, y = PCL_Total,
  type = "nonparametric",
  title = "PTSD Total")

ggstatsplot::ggbetweenstats(
  data = Data,
  x = sectie_categ, y = DASS_A,
  type = "nonparametric",
  title = "Anxiety")

ggstatsplot::ggbetweenstats(
  data = Data,
  x = sectie_categ, y = DASS_S,
  type = "nonparametric",
  title = "Stress")

ggstatsplot::ggbetweenstats(
  data = Data,
  x = sectie_categ, y = DASS_D,
  type = "nonparametric",
  title = "Depression")

8 Tests - Item Sectii & Cutoff scores

ggstatsplot::ggpiestats(
  data = Data,
  x = sectie_categ, y = PCLAlg,
  type = "nonparametric",
  title = "PTSD algo")

ggstatsplot::ggpiestats(
  data = Data,
  x = sectie_categ, y = PCL_cut,
  type = "nonparametric",
  title = "PTSD cutoff")

ggstatsplot::ggpiestats(
  data = Data,
  x = sectie_categ, y = MBI_cut,
  type = "nonparametric",
  title = "MBI cutoff")

9 Session Info

R version 3.6.1 (2019-07-05)
Platform: x86_64-w64-mingw32/x64 (64-bit)
Running under: Windows 8.1 x64 (build 9600)

Matrix products: default

locale:
[1] LC_COLLATE=Romanian_Romania.1250  LC_CTYPE=Romanian_Romania.1250    LC_MONETARY=Romanian_Romania.1250 LC_NUMERIC=C                     
[5] LC_TIME=Romanian_Romania.1250    

attached base packages:
[1] stats     graphics  grDevices utils     datasets  methods   base     

other attached packages:
 [1] dlookr_0.4.3               statsExpressions_1.0.0     ggstatsplot_0.7.1          DataExplorer_0.8.2         performance_0.7.0          rlang_0.4.10              
 [7] pwr_1.2-2                  emmeans_1.5.4              broom_0.7.5                rstatix_0.7.0              rio_0.5.26                 scales_1.1.1              
[13] ggpubr_0.4.0               tadaatoolbox_0.16.1        summarytools_0.8.8         PerformanceAnalytics_1.5.2 xts_0.11-2                 zoo_1.8-4                 
[19] psych_2.0.12               forcats_0.5.1              stringr_1.4.0              dplyr_1.0.5                purrr_0.3.4                readr_1.4.0               
[25] tidyr_1.1.3                tibble_3.1.0               ggplot2_3.3.3              tidyverse_1.3.0            papaja_0.1.0.9997          pacman_0.5.1              

loaded via a namespace (and not attached):
  [1] estimability_1.3          coda_0.19-2               acepack_1.4.1             knitr_1.31                multcomp_1.4-8            data.table_1.14.0        
  [7] rpart_4.1-15              RCurl_1.95-4.11           generics_0.1.0            TH.data_1.0-9             correlation_0.6.0         webshot_0.5.1            
 [13] xml2_1.3.2                lubridate_1.7.4           httpuv_1.5.5              assertthat_0.2.1          viridis_0.5.1             WRS2_1.1-1               
 [19] xfun_0.22                 hms_1.0.0                 evaluate_0.14             promises_1.2.0.1          fansi_0.4.2               dbplyr_2.1.0             
 [25] readxl_1.3.1              igraph_1.2.6              DBI_1.0.0                 tmvnsim_1.0-2             htmlwidgets_1.5.3         reshape_0.8.8            
 [31] kSamples_1.2-9            Rmpfr_0.7-1               paletteer_1.3.0           ellipsis_0.3.1            corrplot_0.84             backports_1.2.1          
 [37] insight_0.13.1            ggcorrplot_0.1.3          prismatic_1.0.0           rapportools_1.0           libcoin_1.0-2             vctrs_0.3.6              
 [43] prettydoc_0.4.1           abind_1.4-5               withr_2.4.1               pryr_0.1.4                RcmdrMisc_2.5-1           checkmate_1.8.5          
 [49] mnormt_2.0.2              svglite_1.2.1             cluster_2.1.1             crayon_1.4.1              pkgconfig_2.0.3           SuppDists_1.1-9.4        
 [55] labeling_0.4.2            nlme_3.1-140              nnet_7.3-12               lifecycle_1.0.0           miniUI_0.1.1.1            MatrixModels_0.4-1       
 [61] sandwich_2.5-0            extrafontdb_1.0           modelr_0.1.8              cellranger_1.1.0          matrixStats_0.54.0        partykit_1.2-13          
 [67] Matrix_1.2-17             mc2d_0.1-18               carData_3.0-2             boot_1.3-22               reprex_1.0.0              base64enc_0.1-3          
 [73] viridisLite_0.3.0         PMCMRplus_1.9.0           parameters_0.12.0         rootSolve_1.8.2.1         bitops_1.0-6              pander_0.6.3             
 [79] ggExtra_0.8               multcompView_0.1-7        ggsignif_0.6.1            memoise_1.1.0             magrittr_2.0.1            plyr_1.8.6               
 [85] compiler_3.6.1            rstantools_2.1.1          kableExtra_1.3.4          RColorBrewer_1.1-2        snakecase_0.9.2           cli_2.3.1                
 [91] patchwork_1.1.1           pbapply_1.3-4             htmlTable_1.12            Formula_1.2-3             MASS_7.3-51.4             tidyselect_1.1.0         
 [97] stringi_1.5.3             pixiedust_0.9.1           yaml_2.2.1                latticeExtra_0.6-28       ggrepel_0.9.1             grid_3.6.1               
[103] tools_3.6.1               lmom_2.8                  parallel_3.6.1            rstudioapi_0.13           foreign_0.8-71            inum_1.0-0               
[109] janitor_2.1.0             gridExtra_2.3             ipmisc_6.0.0              gld_2.6.2                 pairwiseComparisons_3.1.3 farver_2.1.0             
[115] digest_0.6.27             shiny_1.2.0               nortest_1.0-4             quadprog_1.5-5            networkD3_0.4             BWStest_0.2.2            
[121] Rcpp_1.0.6                car_3.0-10                BayesFactor_0.9.12-4.2    later_1.1.0.1             httr_1.4.2                gdtools_0.1.7            
[127] effectsize_0.4.4          colorspace_2.0-0          rvest_1.0.0               fs_1.5.0                  splines_3.6.1             rematch2_2.1.2           
[133] expm_0.999-3              Exact_2.1                 xtable_1.8-4              gmp_0.5-13.2              jsonlite_1.7.2            zeallot_0.1.0            
[139] R6_2.5.0                  Hmisc_4.1-1               pillar_1.5.1              htmltools_0.5.1.1         mime_0.10                 glue_1.4.2               
[145] class_7.3-15              codetools_0.2-16          mvtnorm_1.1-1             utf8_1.2.1                lattice_0.20-38           hrbrthemes_0.8.0         
[151] curl_4.3                  DescTools_0.99.40         gtools_3.8.1              zip_1.0.0                 openxlsx_4.1.0            Rttf2pt1_1.3.8           
[157] survival_2.44-1.1         rmarkdown_2.7             munsell_0.5.0             e1071_1.7-0               haven_2.3.1               gtable_0.3.0             
[163] bayestestR_0.8.2          extrafont_0.17           

 

---

A work by Claudiu Papasteri

claudiu.papasteri@gmail.com